This chapter focuses on the "big data" concept and application in clinical medicine and public health, hypothesis testing and statistical significance, and biological relevance as effect size, namely, absolute and relative measures of evidence. It addresses models and model specification and describes the elements of model building in hypothesis testing as well as appropriate selection of a model that fit the data. The chapter aims to assumptions and the rationale behind models and their conformation to biologic and social realities in evidence discovery. The emergence of "big data," complexities in disease etiology and therapeutics, and the reliability and validity issues in evidence discovery signals some departure from traditional foundation of statistics as a tool in data collection, processing, analysis, and interpretation. With these challenges, biostatistics needs to critically examine the following: Big data and its implication in clinical decision-making in improving care and safety, reality is statistical modeling of clinical and translational research data, and tabulation/stratification versus regression model.